Exploration of National Climatic Data Center Storm Events Data

# plot for the top 20 by total of fatalities and injuries
g <- ggplot(state_harm, aes(x = values,
                 y = reorder(state_name, number_of_events),
                 colour = label),
                 size = 3, shape = 22) + 
  
  theme_economist() + 
  
  scale_colour_stata() +
  
  geom_point() +
  
  labs(x = NULL,
       y = NULL,
       colour = NULL,
       title = "Destructive Weather Events in the United States",
       subtitle = "Source: National Climatic Data Center Storm Events 1950 - 2011",
       caption = "*Damages are estimates\n1950-54 only tornado events recorded\n 1955-92 only tornado, thunderstorm wind and hail events keyed to digital\n1993-95 only tornado, thunderstorm wind and hail events keyed to digital") +
  
  guides(fill = guide_legend(title = NULL)) + 
  
  scale_fill_discrete(labels = c("Fatalities",
                                 "Injuries",
                                 "Events",
                                 "Damages $10,000s")) +
  
  theme(
    legend.position = "bottom",
    panel.grid.major.x = element_line(colour = "white",
                                      size = 1,
                                      linetype = "dotted")) + 
  
  scale_x_log10(breaks = c(1e1, 1e2, 1e3, 1e4, 1e5, 1e6, 1e7),
                labels = c("10", "100", "1,000","10,000", "100,000", "1,000,000", "10,000,000"))

ggplotly(g)